Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the presence of class and method definitions in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Class constructors or initialization methods

    np_acts-logits-general · gemini-2.0-flash

    object initialization and construction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.57
     (
    -0.46
     get
    -0.43
    <bos>
    -0.43
     from
    -0.43
     “
    -0.42
     
    -0.42
     "
    -0.41
     vanaf
    -0.41
     henne
    -0.41
    POSITIVE LOGITS
    SharedDtor
    1.03
     ProtoMessage
    1.02
    SharedCtor
    1.01
     חיצוניים
    0.94
     JpaRepository
    0.93
    BeginInit
    0.91
     ―――――
    0.90
     ExecuteAsync
    0.89
    initComponents
    0.89
     consultato
    0.88
    Act Density 0.060%

    No Known Activations